The Integration of Dependency Relation Classification and Semantic Role Labeling Using Bilayer Maximum Entropy Markov Models. Sun, W., Li, H., & Sui, Z. In Proceedings of the Twelfth Conference on Computational Natural Language Learning CoNLL 08, pages 243-247, 2008. Association for Computational Linguistics.
The Integration of Dependency Relation Classification and Semantic Role Labeling Using Bilayer Maximum Entropy Markov Models [link]Website  abstract   bibtex   
This paper describes a system to solve the joint learning of syntactic and semantic dependencies. An directed graphical model is put forward to integrate dependency relation classification and semantic role labeling. We present a bilayer directed graph to express probabilistic relationships between syntactic and semantic relations. Maximum Entropy Markov Models are implemented to estimate conditional probability distribution and to do inference. The submitted model yields 76.28% macro-average F1 performance, for the joint task, 85.75% syntactic dependencies LAS and 66.61% semantic dependencies F1.
@inProceedings{
 title = {The Integration of Dependency Relation Classification and Semantic Role Labeling Using Bilayer Maximum Entropy Markov Models},
 type = {inProceedings},
 year = {2008},
 identifiers = {[object Object]},
 pages = {243-247},
 issue = {August},
 websites = {http://portal.acm.org/citation.cfm?doid=1596324.1596368},
 publisher = {Association for Computational Linguistics},
 id = {ef8396da-5cc9-31dd-a985-269bfdf7ef69},
 created = {2012-04-01T16:32:49.000Z},
 file_attached = {false},
 profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
 group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
 last_modified = {2017-03-14T14:36:19.698Z},
 tags = {semantic role labeling},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Sun2008},
 private_publication = {false},
 abstract = {This paper describes a system to solve the joint learning of syntactic and semantic dependencies. An directed graphical model is put forward to integrate dependency relation classification and semantic role labeling. We present a bilayer directed graph to express probabilistic relationships between syntactic and semantic relations. Maximum Entropy Markov Models are implemented to estimate conditional probability distribution and to do inference. The submitted model yields 76.28% macro-average F1 performance, for the joint task, 85.75% syntactic dependencies LAS and 66.61% semantic dependencies F1.},
 bibtype = {inProceedings},
 author = {Sun, Weiwei and Li, Hongzhan and Sui, Zhifang},
 booktitle = {Proceedings of the Twelfth Conference on Computational Natural Language Learning CoNLL 08}
}

Downloads: 0